Web: http://arxiv.org/abs/2205.15117

Sept. 16, 2022, 1:12 a.m. | Yangze Zhou, Gitta Kutyniok, Bruno Ribeiro

cs.LG updates on arXiv.org arxiv.org

This work provides the first theoretical study on the ability of graph
Message Passing Neural Networks (gMPNNs) -- such as Graph Neural Networks
(GNNs) -- to achieve counterfactually-invariant representations for inductive
out-of-distribution (OOD) link prediction tasks, where deployment (test) graph
sizes are larger than training graphs. We first prove non-asymptotic bounds
showing that link predictors based on permutation-equivariant (structural) node
embeddings obtained by gMPNNs can converge to a random guess as test graphs get
larger. We then propose a theoretically-sound …

arxiv gnns graphs link prediction prediction test

More from arxiv.org / cs.LG updates on arXiv.org

Machine Learning Product Manager (Canada, Remote)

@ FreshBooks | Canada

Data Engineer

@ Amazon.com | Irvine, California, USA

Senior Autonomy Behavior II, Performance Assessment Engineer

@ Cruise LLC | San Francisco, CA

Senior Data Analytics Engineer

@ Intercom | Dublin, Ireland

Data Analyst Intern

@ ADDX | Singapore

Data Science Analyst - Consumer

@ Yelp | London, England, United Kingdom

Senior Data Analyst - Python+Hadoop

@ Capco | India - Bengaluru

DevOps Engineer, Data Team

@ SingleStore | Hyderabad, India

Software Engineer (Machine Learning, AI Platform)

@ Phaidra | Remote

Sr. UI/UX Designer - Artificial Intelligence (ID:1213)

@ Truelogic Software | Remote, anywhere in LATAM

Analytics Engineer

@ carwow | London, England, United Kingdom

HRIS Data Analyst

@ SecurityScorecard | Remote